English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

It is well-known that the most existing machine learning (ML)-basedsafety-critical applications are vulnerable to carefully crafted inputinstances called adversarial examples (AXs). An adversary can convenientlyattack these target systems from digital as well as physical worlds. This paperaims to the generation of robust physical AXs against face recognition systems.We present a novel smoothness loss function and a patch-noise combo attack forrealizing powerful physical AXs. The smoothness loss interjects the concept ofdelayed constraints during the attack generation process, thereby causingbetter handling of optimization complexity and smoother AXs for the physicaldomain. The patch-noise combo attack combines patch noise and imperceptiblysmall noises from different distributions to generate powerfulregistration-based physical AXs. An extensive experimental analysis found thatour smoothness loss results in robust and more transferable digital andphysical AXs than the conventional techniques. Notably, our smoothness lossresults in a 1.17 and 1.97 times better mean attack success rate (ASR) inphysical white-box and black-box attacks, respectively. Our patch-noise comboattack furthers the performance gains and results in 2.39 and 4.74 times highermean ASR than conventional technique in physical world white-box and black-boxattacks, respectively.

Powerful Physical Adversarial Examples Against Practical Face Recognition Systems